Qwen3-1.7B-4bit-AWQ/args.json

{
  "model": "Qwen/Qwen3-1.7B-Base",
  "model_type": "qwen3",
  "model_revision": null,
  "task_type": "causal_lm",
  "torch_dtype": "float16",
  "attn_impl": null,
  "num_labels": null,
  "problem_type": null,
  "rope_scaling": null,
  "device_map": null,
  "max_memory": {},
  "local_repo_path": null,
  "init_strategy": null,
  "template": "qwen3",
  "system": null,
  "max_length": 2048,
  "truncation_strategy": "delete",
  "max_pixels": null,
  "agent_template": null,
  "norm_bbox": null,
  "use_chat_template": true,
  "padding_free": false,
  "padding_side": "right",
  "loss_scale": "default",
  "sequence_parallel_size": 1,
  "response_prefix": null,
  "template_backend": "swift",
  "dataset": [
    "AI-ModelScope/alpaca-gpt4-data-zh"
  ],
  "val_dataset": [],
  "split_dataset_ratio": 0.01,
  "data_seed": 42,
  "dataset_num_proc": 1,
  "load_from_cache_file": true,
  "dataset_shuffle": true,
  "val_dataset_shuffle": false,
  "streaming": false,
  "interleave_prob": null,
  "stopping_strategy": "first_exhausted",
  "shuffle_buffer_size": 1000,
  "download_mode": "reuse_dataset_if_exists",
  "columns": {},
  "strict": false,
  "remove_unused_columns": true,
  "model_name": null,
  "model_author": null,
  "custom_dataset_info": [],
  "quant_method": "awq",
  "quant_bits": 4,
  "hqq_axis": null,
  "bnb_4bit_compute_dtype": "float32",
  "bnb_4bit_quant_type": "nf4",
  "bnb_4bit_use_double_quant": true,
  "bnb_4bit_quant_storage": null,
  "max_new_tokens": null,
  "temperature": null,
  "top_k": null,
  "top_p": null,
  "repetition_penalty": null,
  "num_beams": 1,
  "stream": false,
  "stop_words": [],
  "logprobs": false,
  "top_logprobs": null,
  "ckpt_dir": null,
  "lora_modules": [],
  "tuner_backend": "peft",
  "train_type": "lora",
  "adapters": [],
  "external_plugins": [],
  "seed": 42,
  "model_kwargs": {},
  "load_args": true,
  "load_data_args": false,
  "packing": false,
  "packing_cache": null,
  "custom_register_path": [],
  "use_hf": false,
  "hub_token": null,
  "ddp_timeout": 18000000,
  "ddp_backend": null,
  "ignore_args_error": false,
  "use_swift_lora": false,
  "merge_lora": false,
  "safe_serialization": true,
  "max_shard_size": "5GB",
  "output_dir": "/home/tj/models/Qwen3-1.7B-4bit-AWQ",
  "quant_n_samples": 256,
  "quant_batch_size": 1,
  "group_size": 128,
  "to_ollama": false,
  "to_mcore": false,
  "to_hf": false,
  "mcore_model": null,
  "thread_count": null,
  "test_convert_precision": false,
  "push_to_hub": false,
  "hub_model_id": null,
  "hub_private_repo": false,
  "commit_message": "update files",
  "to_peft_format": false,
  "exist_ok": false,
  "rank": -1,
  "local_rank": -1,
  "global_world_size": 1,
  "local_world_size": 1,
  "model_suffix": "Qwen3-1.7B-Base",
  "model_info": "ModelInfo(model_type='qwen3', model_dir='/home/tj/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B-Base', torch_dtype=torch.float16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
  "model_meta": "ModelMeta(model_type='qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B-Base', hf_model_id='Qwen/Qwen3-0.6B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-Base', hf_model_id='Qwen/Qwen3-1.7B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Base', hf_model_id='Qwen/Qwen3-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-Base', hf_model_id='Qwen/Qwen3-8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-Base', hf_model_id='Qwen/Qwen3-14B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B', hf_model_id='Qwen/Qwen3-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B', hf_model_id='Qwen/Qwen3-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B-FP8', hf_model_id='Qwen/Qwen3-0.6B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-FP8', hf_model_id='Qwen/Qwen3-1.7B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-FP8', hf_model_id='Qwen/Qwen3-4B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-FP8', hf_model_id='Qwen/Qwen3-8B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-FP8', hf_model_id='Qwen/Qwen3-14B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-FP8', hf_model_id='Qwen/Qwen3-32B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-AWQ', hf_model_id='Qwen/Qwen3-4B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-AWQ', hf_model_id='Qwen/Qwen3-8B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-AWQ', hf_model_id='Qwen/Qwen3-14B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-AWQ', hf_model_id='Qwen/Qwen3-32B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-32B-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3', get_function=<function get_model_tokenizer_with_flash_attn at 0x71fdbfba8a60>, model_arch='llama', architectures=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
  "model_dir": "/home/tj/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B-Base",
  "hub": "<class 'swift.hub.hub.MSHub'>"
}